相关论文: AfriMTEB and AfriE5: Benchmarking and Adapting Tex…

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo,…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

Tasks such as semantic search and clustering on crisis-related social media texts enhance our comprehension of crisis discourse, aiding decision-making and targeted interventions. Pre-trained language models have advanced performance in…

This paper describes a semi-supervised system that jointly learns verbal multiword expressions (VMWEs) and dependency parse trees as an auxiliary task. The model benefits from pre-trained multilingual BERT. BERT hidden layers are shared…

We present an extensive evaluation of three recently proposed methods for contextualized embeddings on 89 corpora in 54 languages of the Universal Dependencies 2.3 in three tasks: POS tagging, lemmatization, and dependency parsing.…

Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (\eg African languages) are often evaluated only on…

Large Language Models (LLMs) have advanced machine translation but remain vulnerable to hallucinations. Unfortunately, existing MT benchmarks are not capable of exposing failures in multilingual LLMs. To disclose hallucination in…

Instruction-following capability has become a major ability to be evaluated for Large Language Models (LLMs). However, existing datasets, such as IFEval, are either predominantly monolingual and centered on English or simply machine…

We introduce the first highly multilingual speech and American Sign Language (ASL) comprehension dataset by extending BELEBELE. Our dataset covers 74 spoken languages at the intersection of BELEBELE and FLEURS, and one sign language (ASL).…

Current sentence embedding evaluations typically rely on static test beds like the Massive Text Embedding Benchmark (MTEB). While invaluable, repeated tuning on a fixed suite can inflate reported scores and obscure real-world robustness. We…

Audio is a critical component of multimodal perception, and any truly intelligent system must demonstrate a wide range of auditory capabilities. These capabilities include transcription, classification, retrieval, reasoning, segmentation,…

Arabic poetry, with its rich linguistic features and profound cultural significance, presents a unique challenge to the Natural Language Processing (NLP) field. The complexity of its structure and context necessitates advanced computational…

This paper introduces TurkEmbed, a novel Turkish language embedding model designed to outperform existing models, particularly in Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. Current Turkish embedding models…

African languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine translation for…

Stopwords are fundamental in Natural Language Processing (NLP) techniques for information retrieval. One of the common tasks in preprocessing of text data is the removal of stopwords. Currently, while high-resource languages like English…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do…

In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training…

Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks. While many natural language understanding challenges can…

Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few…